ClawHub
Back to skill

Security audit

Meeting Minutes

Security checks across malware telemetry and agentic risk

Overview

This is a local meeting-minutes helper with some overly broad routing language, but no evidence of hidden data access, network use, persistence, or destructive behavior.

Install this only for turning provided meeting transcripts into structured minutes. Treat transcripts and generated minutes as sensitive workspace data, especially for medical or confidential meetings, and invoke the skill explicitly for meeting-minutes work rather than unrelated workflow orchestration or general writing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The 'When to Use' section is so broad that it encourages use for loosely related tasks rather than a narrowly defined transcript-to-minutes workflow. Overbroad invocation guidance increases the chance the skill is selected for inappropriate inputs or adjacent tasks, which can lead to unsafe processing, disclosure of sensitive meeting content, or reliance on outputs outside the skill's validated scope.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The phrase at this location allows the skill to be invoked for vaguely defined 'other workflows,' which can cause routing beyond the intended meeting-minutes use case. In agent settings, overly broad invocation criteria can lead to unintended execution, scope drift, and outputs that omit safeguards or assumptions appropriate to the actual task.

Vague Triggers

Medium
Confidence
87% confidence
Finding
This description is ambiguous about the skill's operational boundary, which increases the chance that an orchestrator or user will invoke it for tasks outside its validated scope. The included audit context makes this more concerning because the stress case already recorded boundary-handling failures, showing that ambiguity is not merely theoretical.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.